[V0 Deprecation] Remove V0 sampling metadata (#25345)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
This commit is contained in:
@@ -53,7 +53,6 @@ from vllm.model_executor.model_loader.weight_utils import (
|
||||
default_weight_loader, sharded_weight_loader)
|
||||
from vllm.model_executor.models.mamba_cache import MambaCacheParams
|
||||
from vllm.model_executor.models.qwen2_moe import Qwen2MoeMLP as Qwen3NextMLP
|
||||
from vllm.model_executor.sampling_metadata import SamplingMetadata
|
||||
from vllm.model_executor.utils import set_weight_attrs
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.sequence import IntermediateTensors
|
||||
@@ -1208,10 +1207,8 @@ class Qwen3NextForCausalLM(nn.Module, HasInnerState, SupportsLoRA, SupportsPP,
|
||||
def compute_logits(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
sampling_metadata: SamplingMetadata,
|
||||
) -> Optional[torch.Tensor]:
|
||||
return self.logits_processor(self.lm_head, hidden_states,
|
||||
sampling_metadata)
|
||||
return self.logits_processor(self.lm_head, hidden_states)
|
||||
|
||||
def load_weights(self, weights: Iterable[tuple[str,
|
||||
torch.Tensor]]) -> set[str]:
|
||||
|
||||
Reference in New Issue
Block a user